Automated Identification of Acute Aortic Syndromes in Computed Tomography Images

2. The method of claim 1, wherein each of the set of the variation values for each of the plurality of locations include a range of representative radiodensity values within the location.

3. The method of claim 1, wherein determining the parameter representing the likelihood that the patient is experiencing an acute aortic syndrome includes determining a parameter representing the likelihood that the patient is experiencing an acute aortic syndrome related to changes in the ascending aorta.

5. The method of claim 4, wherein calculating the value representing the variation in radiodensity values comprises determining a maximum variation between any two of the representative radiodensity measurements for the plurality of regions.

6. The method of claim 4, wherein obtaining a representative radiodensity measurement for each of the plurality of regions comprises calculating an average radiodensity value across at least a portion of the region.

7. The method of claim 1, wherein the derived model is a decision tree, and the parameter representing the likelihood that the patient is experiencing an acute aortic syndrome is a categorical parameter.

8. The method of claim 1, wherein determining the parameter representing the likelihood that the patient is experiencing an acute aortic syndrome from the set of variation values comprises determining the parameter representing the likelihood that the patient is experiencing an acute aortic syndrome from the set of variation values and a set of at least one clinical parameter associated with the patient.

9. The method of claim 8, wherein the set of at least one clinical parameter comprises one of age, sex, aortic diameter, blood pressure, and a parameter representing a medical history of the patient.

11. The system of claim 10, wherein the feature extractor determines the value representing a variation in radiodensity values within each of the plurality of locations as a range of representative radiodensity values within the location.

12. The system of claim 10, wherein the feature extractor determines the representative radiodensity measurement for each of the plurality of regions as an average radiodensity value for a subregion lying entirely within the region.

13. The system of claim 10, wherein the derived model is a machine learning model.

14. The system of claim 10, wherein the feature extractor determines the value representing a variation in radiodensity values within each of the plurality of locations as an interquartile range of representative radiodensity values within the location.

15. The system of claim 10, wherein the feature extractor determines the value representing a variation in radiodensity values within each of the plurality of locations as a standard deviation of representative radiodensity values within the location.

16. The system of claim 15, wherein the feature extractor determines the range value for representative HU values within each of the plurality of locations by determining representative HU measurements for each of a plurality of regions within each location and calculating the range value for each location from the representative HU measurements for the plurality of regions.